3D Semantic Label Results - ScanNet Benchmark

The 3D semantic labeling task involves predicting a semantic labeling of a 3D scan mesh.

Evaluation and metrics

Our evaluation ranks all methods according to the PASCAL VOC intersection-over-union metric (IoU). IoU = TP/(TP+FP+FN), where TP, FP, and FN are the numbers of true positive, false positive, and false negative pixels, respectively. Predicted labels are evaluated per-vertex over the respective 3D scan mesh; for 3D approaches that operate on other representations like grids or points, the predicted labels should be mapped onto the mesh vertices (e.g., one such example for grid to mesh vertices is provided in the evaluation helpers).

This table lists the benchmark results for the 3D semantic label scenario.

Method	avg iou	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	floor	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	wall	window

PTv3-PPT-ALC	0.798 1	0.911 11	0.812 21	0.854 7	0.770 12	0.856 15	0.555 15	0.943 1	0.660 24	0.735 2	0.979 1	0.606 7	0.492 1	0.792 4	0.934 3	0.841 2	0.819 5	0.716 8	0.947 10	0.906 1	0.822 1

PTv3 ScanNet	0.794 2	0.941 4	0.813 20	0.851 10	0.782 6	0.890 3	0.597 1	0.916 5	0.696 9	0.713 5	0.979 1	0.635 2	0.384 3	0.793 3	0.907 10	0.821 5	0.790 34	0.696 13	0.967 3	0.903 2	0.805 2
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral)
DITR ScanNet	0.793 3	0.811 40	0.852 2	0.889 1	0.774 9	0.907 1	0.592 2	0.927 3	0.719 1	0.718 3	0.961 17	0.652 1	0.348 12	0.817 1	0.927 5	0.795 9	0.824 2	0.749 1	0.948 9	0.887 7	0.771 11

PonderV2	0.785 4	0.978 1	0.800 29	0.833 27	0.788 4	0.853 20	0.545 19	0.910 8	0.713 2	0.705 6	0.979 1	0.596 9	0.390 2	0.769 15	0.832 44	0.821 5	0.792 33	0.730 2	0.975 1	0.897 5	0.785 6
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
Mix3D	0.781 5	0.964 2	0.855 1	0.843 19	0.781 7	0.858 13	0.575 7	0.831 36	0.685 15	0.714 4	0.979 1	0.594 10	0.310 29	0.801 2	0.892 18	0.841 2	0.819 5	0.723 5	0.940 15	0.887 7	0.725 27
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3D	0.779 6	0.861 22	0.818 15	0.836 24	0.790 3	0.875 5	0.576 6	0.905 9	0.704 6	0.739 1	0.969 11	0.611 3	0.349 11	0.756 25	0.958 1	0.702 49	0.805 17	0.708 9	0.916 36	0.898 4	0.801 3

TTT-KD	0.773 7	0.646 95	0.818 15	0.809 39	0.774 9	0.878 4	0.581 3	0.943 1	0.687 13	0.704 7	0.978 5	0.607 6	0.336 18	0.775 11	0.912 8	0.838 4	0.823 3	0.694 14	0.967 3	0.899 3	0.794 5
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla: TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models.
ResLFE_HDS	0.772 8	0.939 5	0.824 7	0.854 7	0.771 11	0.840 34	0.564 11	0.900 11	0.686 14	0.677 14	0.961 17	0.537 34	0.348 12	0.769 15	0.903 12	0.785 13	0.815 8	0.676 25	0.939 16	0.880 13	0.772 10

OctFormer	0.766 9	0.925 8	0.808 25	0.849 12	0.786 5	0.846 30	0.566 10	0.876 18	0.690 11	0.674 16	0.960 19	0.576 20	0.226 70	0.753 27	0.904 11	0.777 15	0.815 8	0.722 6	0.923 31	0.877 16	0.776 9
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
PPT-SpUNet-Joint	0.766 9	0.932 6	0.794 35	0.829 29	0.751 25	0.854 18	0.540 23	0.903 10	0.630 37	0.672 17	0.963 15	0.565 24	0.357 9	0.788 5	0.900 14	0.737 29	0.802 18	0.685 19	0.950 7	0.887 7	0.780 7
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
CU-Hybrid Net	0.764 11	0.924 9	0.819 13	0.840 21	0.757 20	0.853 20	0.580 4	0.848 29	0.709 4	0.643 27	0.958 23	0.587 15	0.295 37	0.753 27	0.884 22	0.758 22	0.815 8	0.725 4	0.927 27	0.867 26	0.743 18

OccuSeg+Semantic	0.764 11	0.758 61	0.796 33	0.839 22	0.746 29	0.907 1	0.562 12	0.850 28	0.680 17	0.672 17	0.978 5	0.610 4	0.335 20	0.777 9	0.819 48	0.847 1	0.830 1	0.691 16	0.972 2	0.885 10	0.727 25

O-CNN	0.762 13	0.924 9	0.823 8	0.844 18	0.770 12	0.852 22	0.577 5	0.847 31	0.711 3	0.640 31	0.958 23	0.592 11	0.217 76	0.762 20	0.888 19	0.758 22	0.813 12	0.726 3	0.932 25	0.868 25	0.744 17
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong: O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. SIGGRAPH 2017
DiffSegNet	0.758 14	0.725 77	0.789 40	0.843 19	0.762 16	0.856 15	0.562 12	0.920 4	0.657 27	0.658 21	0.958 23	0.589 13	0.337 17	0.782 6	0.879 23	0.787 11	0.779 39	0.678 21	0.926 29	0.880 13	0.799 4

DTC	0.757 15	0.843 28	0.820 11	0.847 15	0.791 2	0.862 11	0.511 36	0.870 21	0.707 5	0.652 23	0.954 39	0.604 8	0.279 47	0.760 21	0.942 2	0.734 30	0.766 48	0.701 12	0.884 58	0.874 22	0.736 19

OA-CNN-L_ScanNet20	0.756 16	0.783 47	0.826 6	0.858 5	0.776 8	0.837 37	0.548 18	0.896 14	0.649 29	0.675 15	0.962 16	0.586 16	0.335 20	0.771 14	0.802 53	0.770 18	0.787 36	0.691 16	0.936 20	0.880 13	0.761 13

ConDaFormer	0.755 17	0.927 7	0.822 9	0.836 24	0.801 1	0.849 25	0.516 33	0.864 25	0.651 28	0.680 13	0.958 23	0.584 18	0.282 44	0.759 23	0.855 34	0.728 32	0.802 18	0.678 21	0.880 63	0.873 23	0.756 15
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
PNE	0.755 17	0.786 45	0.835 5	0.834 26	0.758 18	0.849 25	0.570 9	0.836 35	0.648 30	0.668 19	0.978 5	0.581 19	0.367 7	0.683 38	0.856 32	0.804 7	0.801 22	0.678 21	0.961 5	0.889 6	0.716 33
P. Hermosilla: Point Neighborhood Embeddings.
PointTransformerV2	0.752 19	0.742 68	0.809 24	0.872 2	0.758 18	0.860 12	0.552 16	0.891 16	0.610 44	0.687 8	0.960 19	0.559 28	0.304 32	0.766 18	0.926 6	0.767 19	0.797 26	0.644 36	0.942 13	0.876 19	0.722 29
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
DMF-Net	0.752 19	0.906 14	0.793 37	0.802 45	0.689 43	0.825 51	0.556 14	0.867 22	0.681 16	0.602 48	0.960 19	0.555 30	0.365 8	0.779 8	0.859 29	0.747 25	0.795 30	0.717 7	0.917 35	0.856 34	0.764 12
C.Yang, Y.Yan, W.Zhao, J.Ye, X.Yang, A.Hussain, B.Dong, K.Huang: Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation. ICONIP 2023
BPNet	0.749 21	0.909 12	0.818 15	0.811 37	0.752 23	0.839 36	0.485 51	0.842 32	0.673 19	0.644 26	0.957 28	0.528 40	0.305 31	0.773 12	0.859 29	0.788 10	0.818 7	0.693 15	0.916 36	0.856 34	0.723 28
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PointConvFormer	0.749 21	0.793 43	0.790 38	0.807 41	0.750 27	0.856 15	0.524 29	0.881 17	0.588 56	0.642 30	0.977 9	0.591 12	0.274 50	0.781 7	0.929 4	0.804 7	0.796 27	0.642 37	0.947 10	0.885 10	0.715 34
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
MSP	0.748 23	0.623 98	0.804 27	0.859 4	0.745 30	0.824 53	0.501 40	0.912 7	0.690 11	0.685 10	0.956 30	0.567 23	0.320 26	0.768 17	0.918 7	0.720 37	0.802 18	0.676 25	0.921 33	0.881 12	0.779 8

StratifiedFormer	0.747 24	0.901 15	0.803 28	0.845 17	0.757 20	0.846 30	0.512 35	0.825 39	0.696 9	0.645 25	0.956 30	0.576 20	0.262 61	0.744 33	0.861 28	0.742 27	0.770 46	0.705 10	0.899 48	0.860 31	0.734 20
Xin Lai, Jianhui Liu, Li Jiang, Liwei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia: Stratified Transformer for 3D Point Cloud Segmentation. CVPR 2022
Virtual MVFusion	0.746 25	0.771 55	0.819 13	0.848 14	0.702 41	0.865 10	0.397 88	0.899 12	0.699 7	0.664 20	0.948 60	0.588 14	0.330 22	0.746 32	0.851 38	0.764 20	0.796 27	0.704 11	0.935 21	0.866 27	0.728 23
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
VMNet	0.746 25	0.870 20	0.838 3	0.858 5	0.729 35	0.850 24	0.501 40	0.874 19	0.587 57	0.658 21	0.956 30	0.564 25	0.299 34	0.765 19	0.900 14	0.716 40	0.812 13	0.631 42	0.939 16	0.858 32	0.709 35
Zeyu HU, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai: VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. ICCV 2021 (Oral)
DiffSeg3D2	0.745 27	0.725 77	0.814 19	0.837 23	0.751 25	0.831 45	0.514 34	0.896 14	0.674 18	0.684 11	0.960 19	0.564 25	0.303 33	0.773 12	0.820 47	0.713 43	0.798 25	0.690 18	0.923 31	0.875 20	0.757 14

Retro-FPN	0.744 28	0.842 29	0.800 29	0.767 59	0.740 31	0.836 39	0.541 21	0.914 6	0.672 20	0.626 36	0.958 23	0.552 31	0.272 52	0.777 9	0.886 21	0.696 50	0.801 22	0.674 28	0.941 14	0.858 32	0.717 31
Peng Xiang, Xin Wen, Yu-Shen Liu, Hui Zhang, Yi Fang, Zhizhong Han: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation. ICCV 2023
EQ-Net	0.743 29	0.620 99	0.799 32	0.849 12	0.730 34	0.822 55	0.493 48	0.897 13	0.664 21	0.681 12	0.955 33	0.562 27	0.378 4	0.760 21	0.903 12	0.738 28	0.801 22	0.673 29	0.907 40	0.877 16	0.745 16
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
LRPNet	0.742 30	0.816 37	0.806 26	0.807 41	0.752 23	0.828 49	0.575 7	0.839 34	0.699 7	0.637 33	0.954 39	0.520 43	0.320 26	0.755 26	0.834 42	0.760 21	0.772 43	0.676 25	0.915 38	0.862 29	0.717 31

SAT	0.742 30	0.860 23	0.765 54	0.819 32	0.769 14	0.848 27	0.533 25	0.829 37	0.663 22	0.631 35	0.955 33	0.586 16	0.274 50	0.753 27	0.896 16	0.729 31	0.760 54	0.666 31	0.921 33	0.855 36	0.733 21

LargeKernel3D	0.739 32	0.909 12	0.820 11	0.806 43	0.740 31	0.852 22	0.545 19	0.826 38	0.594 55	0.643 27	0.955 33	0.541 33	0.263 60	0.723 36	0.858 31	0.775 17	0.767 47	0.678 21	0.933 23	0.848 41	0.694 40
Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN	0.736 33	0.776 51	0.790 38	0.851 10	0.754 22	0.854 18	0.491 50	0.866 23	0.596 54	0.686 9	0.955 33	0.536 35	0.342 15	0.624 53	0.869 25	0.787 11	0.802 18	0.628 43	0.927 27	0.875 20	0.704 37

MinkowskiNet	0.736 33	0.859 24	0.818 15	0.832 28	0.709 39	0.840 34	0.521 31	0.853 27	0.660 24	0.643 27	0.951 50	0.544 32	0.286 42	0.731 34	0.893 17	0.675 58	0.772 43	0.683 20	0.874 70	0.852 39	0.727 25
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA	0.731 35	0.890 16	0.837 4	0.864 3	0.726 36	0.873 6	0.530 28	0.824 40	0.489 90	0.647 24	0.978 5	0.609 5	0.336 18	0.624 53	0.733 63	0.758 22	0.776 41	0.570 68	0.949 8	0.877 16	0.728 23

online3d	0.727 36	0.715 82	0.777 47	0.854 7	0.748 28	0.858 13	0.497 45	0.872 20	0.572 63	0.639 32	0.957 28	0.523 41	0.297 36	0.750 30	0.803 52	0.744 26	0.810 14	0.587 64	0.938 18	0.871 24	0.719 30

SparseConvNet	0.725 37	0.647 94	0.821 10	0.846 16	0.721 37	0.869 7	0.533 25	0.754 61	0.603 50	0.614 40	0.955 33	0.572 22	0.325 24	0.710 37	0.870 24	0.724 35	0.823 3	0.628 43	0.934 22	0.865 28	0.683 43

PointTransformer++	0.725 37	0.727 76	0.811 23	0.819 32	0.765 15	0.841 33	0.502 39	0.814 45	0.621 40	0.623 38	0.955 33	0.556 29	0.284 43	0.620 55	0.866 26	0.781 14	0.757 58	0.648 34	0.932 25	0.862 29	0.709 35

MatchingNet	0.724 39	0.812 39	0.812 21	0.810 38	0.735 33	0.834 42	0.495 47	0.860 26	0.572 63	0.602 48	0.954 39	0.512 45	0.280 46	0.757 24	0.845 40	0.725 34	0.780 38	0.606 53	0.937 19	0.851 40	0.700 39

INS-Conv-semantic	0.717 40	0.751 64	0.759 57	0.812 36	0.704 40	0.868 8	0.537 24	0.842 32	0.609 46	0.608 44	0.953 43	0.534 37	0.293 38	0.616 56	0.864 27	0.719 39	0.793 31	0.640 38	0.933 23	0.845 45	0.663 48

PointMetaBase	0.714 41	0.835 30	0.785 41	0.821 30	0.684 45	0.846 30	0.531 27	0.865 24	0.614 41	0.596 52	0.953 43	0.500 48	0.246 66	0.674 39	0.888 19	0.692 51	0.764 50	0.624 45	0.849 85	0.844 46	0.675 45

contrastBoundary	0.705 42	0.769 58	0.775 48	0.809 39	0.687 44	0.820 58	0.439 76	0.812 46	0.661 23	0.591 54	0.945 68	0.515 44	0.171 95	0.633 50	0.856 32	0.720 37	0.796 27	0.668 30	0.889 55	0.847 42	0.689 41
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic	0.703 43	0.774 53	0.800 29	0.793 50	0.760 17	0.847 29	0.471 55	0.802 49	0.463 97	0.634 34	0.968 13	0.491 51	0.271 54	0.726 35	0.910 9	0.706 45	0.815 8	0.551 80	0.878 65	0.833 47	0.570 80

RFCR	0.702 44	0.889 17	0.745 67	0.813 35	0.672 48	0.818 62	0.493 48	0.815 44	0.623 38	0.610 42	0.947 62	0.470 60	0.249 65	0.594 59	0.848 39	0.705 46	0.779 39	0.646 35	0.892 53	0.823 53	0.611 63
Jingyu Gong, Jiachen Xu, Xin Tan, Haichuan Song, Yanyun Qu, Yuan Xie, Lizhuang Ma: Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning. CVPR2021
One Thing One Click	0.701 45	0.825 34	0.796 33	0.723 66	0.716 38	0.832 44	0.433 78	0.816 42	0.634 35	0.609 43	0.969 11	0.418 86	0.344 14	0.559 71	0.833 43	0.715 41	0.808 16	0.560 74	0.902 45	0.847 42	0.680 44

JSENet	0.699 46	0.881 19	0.762 55	0.821 30	0.667 49	0.800 74	0.522 30	0.792 52	0.613 42	0.607 45	0.935 88	0.492 50	0.205 81	0.576 64	0.853 36	0.691 52	0.758 56	0.652 33	0.872 73	0.828 50	0.649 52
Zeyu HU, Mingmin Zhen, Xuyang BAI, Hongbo Fu, Chiew-lan Tai: JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds. ECCV 2020
One-Thing-One-Click	0.693 47	0.743 67	0.794 35	0.655 89	0.684 45	0.822 55	0.497 45	0.719 71	0.622 39	0.617 39	0.977 9	0.447 73	0.339 16	0.750 30	0.664 79	0.703 48	0.790 34	0.596 57	0.946 12	0.855 36	0.647 53
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-II	0.692 48	0.732 72	0.772 49	0.786 51	0.677 47	0.866 9	0.517 32	0.848 29	0.509 83	0.626 36	0.952 48	0.536 35	0.225 72	0.545 77	0.704 70	0.689 55	0.810 14	0.564 73	0.903 44	0.854 38	0.729 22
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNet	0.690 49	0.884 18	0.754 61	0.795 48	0.647 56	0.818 62	0.422 80	0.802 49	0.612 43	0.604 46	0.945 68	0.462 63	0.189 90	0.563 70	0.853 36	0.726 33	0.765 49	0.632 41	0.904 42	0.821 56	0.606 67
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet	0.688 50	0.704 84	0.741 71	0.754 63	0.656 51	0.829 47	0.501 40	0.741 66	0.609 46	0.548 62	0.950 54	0.522 42	0.371 5	0.633 50	0.756 57	0.715 41	0.771 45	0.623 46	0.861 81	0.814 59	0.658 49
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Net	0.685 51	0.866 21	0.748 64	0.819 32	0.645 58	0.794 77	0.450 66	0.802 49	0.587 57	0.604 46	0.945 68	0.464 62	0.201 84	0.554 73	0.840 41	0.723 36	0.732 69	0.602 55	0.907 40	0.822 55	0.603 70

KP-FCNN	0.684 52	0.847 27	0.758 59	0.784 53	0.647 56	0.814 65	0.473 54	0.772 55	0.605 48	0.594 53	0.935 88	0.450 71	0.181 93	0.587 60	0.805 51	0.690 53	0.785 37	0.614 49	0.882 60	0.819 57	0.632 59
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
DGNet	0.684 52	0.712 83	0.784 42	0.782 55	0.658 50	0.835 41	0.499 44	0.823 41	0.641 32	0.597 51	0.950 54	0.487 53	0.281 45	0.575 65	0.619 83	0.647 72	0.764 50	0.620 48	0.871 76	0.846 44	0.688 42

VACNN++	0.684 52	0.728 75	0.757 60	0.776 56	0.690 42	0.804 72	0.464 60	0.816 42	0.577 62	0.587 55	0.945 68	0.508 47	0.276 49	0.671 40	0.710 68	0.663 63	0.750 62	0.589 62	0.881 61	0.832 49	0.653 51

Superpoint Network	0.683 55	0.851 26	0.728 75	0.800 47	0.653 53	0.806 70	0.468 57	0.804 47	0.572 63	0.602 48	0.946 65	0.453 70	0.239 69	0.519 82	0.822 45	0.689 55	0.762 53	0.595 59	0.895 51	0.827 51	0.630 60

PointContrast_LA_SEM	0.683 55	0.757 62	0.784 42	0.786 51	0.639 60	0.824 53	0.408 83	0.775 54	0.604 49	0.541 64	0.934 92	0.532 38	0.269 56	0.552 74	0.777 55	0.645 75	0.793 31	0.640 38	0.913 39	0.824 52	0.671 46

VI-PointConv	0.676 57	0.770 57	0.754 61	0.783 54	0.621 64	0.814 65	0.552 16	0.758 59	0.571 66	0.557 60	0.954 39	0.529 39	0.268 58	0.530 80	0.682 74	0.675 58	0.719 72	0.603 54	0.888 56	0.833 47	0.665 47
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D	0.673 58	0.789 44	0.748 64	0.763 61	0.635 62	0.814 65	0.407 85	0.747 63	0.581 61	0.573 56	0.950 54	0.484 54	0.271 54	0.607 57	0.754 58	0.649 68	0.774 42	0.596 57	0.883 59	0.823 53	0.606 67

SALANet	0.670 59	0.816 37	0.770 52	0.768 58	0.652 54	0.807 69	0.451 63	0.747 63	0.659 26	0.545 63	0.924 98	0.473 59	0.149 105	0.571 67	0.811 50	0.635 78	0.746 64	0.623 46	0.892 53	0.794 71	0.570 80

O3DSeg	0.668 60	0.822 35	0.771 51	0.496 109	0.651 55	0.833 43	0.541 21	0.761 58	0.555 72	0.611 41	0.966 14	0.489 52	0.370 6	0.388 102	0.580 86	0.776 16	0.751 60	0.570 68	0.956 6	0.817 58	0.646 54

PointASNL	0.666 61	0.703 85	0.781 45	0.751 65	0.655 52	0.830 46	0.471 55	0.769 56	0.474 93	0.537 66	0.951 50	0.475 58	0.279 47	0.635 48	0.698 73	0.675 58	0.751 60	0.553 79	0.816 92	0.806 63	0.703 38
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PointConv	0.666 61	0.781 48	0.759 57	0.699 74	0.644 59	0.822 55	0.475 53	0.779 53	0.564 69	0.504 80	0.953 43	0.428 80	0.203 83	0.586 62	0.754 58	0.661 64	0.753 59	0.588 63	0.902 45	0.813 61	0.642 55
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PPCNN++	0.663 63	0.746 65	0.708 78	0.722 67	0.638 61	0.820 58	0.451 63	0.566 99	0.599 52	0.541 64	0.950 54	0.510 46	0.313 28	0.648 45	0.819 48	0.616 83	0.682 87	0.590 61	0.869 77	0.810 62	0.656 50
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net	0.658 64	0.778 49	0.702 81	0.806 43	0.619 65	0.813 68	0.468 57	0.693 80	0.494 86	0.524 72	0.941 80	0.449 72	0.298 35	0.510 85	0.821 46	0.675 58	0.727 71	0.568 71	0.826 90	0.803 65	0.637 57
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
HPGCNN	0.656 65	0.698 87	0.743 69	0.650 90	0.564 82	0.820 58	0.505 38	0.758 59	0.631 36	0.479 84	0.945 68	0.480 56	0.226 70	0.572 66	0.774 56	0.690 53	0.735 67	0.614 49	0.853 84	0.776 87	0.597 73
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-seg	0.654 66	0.752 63	0.734 73	0.664 87	0.583 77	0.815 64	0.399 87	0.754 61	0.639 33	0.535 68	0.942 78	0.470 60	0.309 30	0.665 41	0.539 89	0.650 67	0.708 77	0.635 40	0.857 83	0.793 73	0.642 55
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Net	0.645 67	0.778 49	0.731 74	0.699 74	0.577 78	0.829 47	0.446 68	0.736 67	0.477 92	0.523 74	0.945 68	0.454 67	0.269 56	0.484 92	0.749 61	0.618 81	0.738 65	0.599 56	0.827 89	0.792 76	0.621 62

PointConv-SFPN	0.641 68	0.776 51	0.703 80	0.721 68	0.557 85	0.826 50	0.451 63	0.672 85	0.563 70	0.483 83	0.943 77	0.425 83	0.162 100	0.644 46	0.726 64	0.659 65	0.709 76	0.572 67	0.875 68	0.786 82	0.559 86

MVPNet	0.641 68	0.831 31	0.715 76	0.671 84	0.590 73	0.781 83	0.394 89	0.679 82	0.642 31	0.553 61	0.937 85	0.462 63	0.256 62	0.649 44	0.406 102	0.626 79	0.691 84	0.666 31	0.877 66	0.792 76	0.608 66
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet	0.640 70	0.717 81	0.701 82	0.692 77	0.576 79	0.801 73	0.467 59	0.716 72	0.563 70	0.459 90	0.953 43	0.429 79	0.169 97	0.581 63	0.854 35	0.605 84	0.710 74	0.550 81	0.894 52	0.793 73	0.575 78

FPConv	0.639 71	0.785 46	0.760 56	0.713 72	0.603 68	0.798 75	0.392 90	0.534 104	0.603 50	0.524 72	0.948 60	0.457 65	0.250 64	0.538 78	0.723 66	0.598 88	0.696 82	0.614 49	0.872 73	0.799 66	0.567 83
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net	0.638 72	0.797 42	0.769 53	0.641 95	0.590 73	0.820 58	0.461 61	0.537 103	0.637 34	0.536 67	0.947 62	0.388 93	0.206 80	0.656 42	0.668 77	0.647 72	0.732 69	0.585 65	0.868 78	0.793 73	0.473 106

PointSPNet	0.637 73	0.734 71	0.692 89	0.714 71	0.576 79	0.797 76	0.446 68	0.743 65	0.598 53	0.437 95	0.942 78	0.403 89	0.150 104	0.626 52	0.800 54	0.649 68	0.697 81	0.557 77	0.846 86	0.777 86	0.563 84

SConv	0.636 74	0.830 32	0.697 85	0.752 64	0.572 81	0.780 85	0.445 70	0.716 72	0.529 76	0.530 69	0.951 50	0.446 74	0.170 96	0.507 87	0.666 78	0.636 77	0.682 87	0.541 87	0.886 57	0.799 66	0.594 74

Supervoxel-CNN	0.635 75	0.656 92	0.711 77	0.719 69	0.613 66	0.757 94	0.444 73	0.765 57	0.534 75	0.566 57	0.928 96	0.478 57	0.272 52	0.636 47	0.531 91	0.664 62	0.645 97	0.508 95	0.864 80	0.792 76	0.611 63

joint point-based	0.634 76	0.614 100	0.778 46	0.667 86	0.633 63	0.825 51	0.420 81	0.804 47	0.467 95	0.561 58	0.951 50	0.494 49	0.291 39	0.566 68	0.458 97	0.579 94	0.764 50	0.559 76	0.838 87	0.814 59	0.598 72
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL	0.632 77	0.731 73	0.688 92	0.675 81	0.591 72	0.784 82	0.444 73	0.565 100	0.610 44	0.492 81	0.949 58	0.456 66	0.254 63	0.587 60	0.706 69	0.599 87	0.665 93	0.612 52	0.868 78	0.791 79	0.579 77

PointNet2-SFPN	0.631 78	0.771 55	0.692 89	0.672 82	0.524 90	0.837 37	0.440 75	0.706 77	0.538 74	0.446 92	0.944 74	0.421 85	0.219 75	0.552 74	0.751 60	0.591 90	0.737 66	0.543 86	0.901 47	0.768 89	0.557 87

APCF-Net	0.631 78	0.742 68	0.687 94	0.672 82	0.557 85	0.792 80	0.408 83	0.665 86	0.545 73	0.508 77	0.952 48	0.428 80	0.186 91	0.634 49	0.702 71	0.620 80	0.706 78	0.555 78	0.873 71	0.798 68	0.581 76
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
3DSM_DMMF	0.631 78	0.626 97	0.745 67	0.801 46	0.607 67	0.751 95	0.506 37	0.729 70	0.565 68	0.491 82	0.866 112	0.434 75	0.197 87	0.595 58	0.630 82	0.709 44	0.705 79	0.560 74	0.875 68	0.740 97	0.491 101

FusionAwareConv	0.630 81	0.604 102	0.741 71	0.766 60	0.590 73	0.747 96	0.501 40	0.734 68	0.503 85	0.527 70	0.919 102	0.454 67	0.323 25	0.550 76	0.420 101	0.678 57	0.688 85	0.544 84	0.896 50	0.795 70	0.627 61
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR	0.628 82	0.800 41	0.625 104	0.719 69	0.545 87	0.806 70	0.445 70	0.597 94	0.448 100	0.519 75	0.938 84	0.481 55	0.328 23	0.489 91	0.499 96	0.657 66	0.759 55	0.592 60	0.881 61	0.797 69	0.634 58

SegGroup_sem	0.627 83	0.818 36	0.747 66	0.701 73	0.602 69	0.764 91	0.385 94	0.629 91	0.490 88	0.508 77	0.931 95	0.409 88	0.201 84	0.564 69	0.725 65	0.618 81	0.692 83	0.539 88	0.873 71	0.794 71	0.548 90
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
dtc_net	0.625 84	0.703 85	0.751 63	0.794 49	0.535 88	0.848 27	0.480 52	0.676 84	0.528 77	0.469 87	0.944 74	0.454 67	0.004 117	0.464 94	0.636 81	0.704 47	0.758 56	0.548 83	0.924 30	0.787 81	0.492 100

SIConv	0.625 84	0.830 32	0.694 87	0.757 62	0.563 83	0.772 89	0.448 67	0.647 89	0.520 79	0.509 76	0.949 58	0.431 78	0.191 89	0.496 89	0.614 84	0.647 72	0.672 91	0.535 90	0.876 67	0.783 83	0.571 79

Weakly-Openseg v3	0.621 86	0.956 3	0.783 44	0.638 96	0.499 93	0.836 39	0.374 96	0.694 79	0.355 110	0.560 59	0.953 43	0.219 115	0.195 88	0.514 83	0.740 62	0.649 68	0.747 63	0.516 92	0.880 63	0.789 80	0.522 96

HPEIN	0.618 87	0.729 74	0.668 95	0.647 92	0.597 71	0.766 90	0.414 82	0.680 81	0.520 79	0.525 71	0.946 65	0.432 76	0.215 77	0.493 90	0.599 85	0.638 76	0.617 102	0.570 68	0.897 49	0.806 63	0.605 69
Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia: Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. ICCV 2019
SPH3D-GCN	0.610 88	0.858 25	0.772 49	0.489 110	0.532 89	0.792 80	0.404 86	0.643 90	0.570 67	0.507 79	0.935 88	0.414 87	0.046 114	0.510 85	0.702 71	0.602 86	0.705 79	0.549 82	0.859 82	0.773 88	0.534 93
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN	0.609 89	0.760 60	0.667 96	0.649 91	0.521 91	0.793 78	0.457 62	0.648 88	0.528 77	0.434 97	0.947 62	0.401 90	0.153 103	0.454 95	0.721 67	0.648 71	0.717 73	0.536 89	0.904 42	0.765 90	0.485 102
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer	0.600 90	0.634 96	0.743 69	0.697 76	0.601 70	0.781 83	0.437 77	0.585 97	0.493 87	0.446 92	0.933 93	0.394 91	0.011 116	0.654 43	0.661 80	0.603 85	0.733 68	0.526 91	0.832 88	0.761 92	0.480 103

LAP-D	0.594 91	0.720 79	0.692 89	0.637 97	0.456 101	0.773 88	0.391 92	0.730 69	0.587 57	0.445 94	0.940 82	0.381 94	0.288 40	0.434 98	0.453 99	0.591 90	0.649 95	0.581 66	0.777 96	0.749 96	0.610 65

DPC	0.592 92	0.720 79	0.700 83	0.602 101	0.480 97	0.762 93	0.380 95	0.713 75	0.585 60	0.437 95	0.940 82	0.369 96	0.288 40	0.434 98	0.509 95	0.590 92	0.639 100	0.567 72	0.772 97	0.755 94	0.592 75
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet	0.589 93	0.766 59	0.659 99	0.683 79	0.470 100	0.740 98	0.387 93	0.620 93	0.490 88	0.476 85	0.922 100	0.355 99	0.245 67	0.511 84	0.511 94	0.571 95	0.643 98	0.493 99	0.872 73	0.762 91	0.600 71

ROSMRF	0.580 94	0.772 54	0.707 79	0.681 80	0.563 83	0.764 91	0.362 98	0.515 105	0.465 96	0.465 89	0.936 87	0.427 82	0.207 79	0.438 96	0.577 87	0.536 98	0.675 90	0.486 100	0.723 103	0.779 84	0.524 95

SD-DETR	0.576 95	0.746 65	0.609 108	0.445 114	0.517 92	0.643 109	0.366 97	0.714 74	0.456 98	0.468 88	0.870 111	0.432 76	0.264 59	0.558 72	0.674 75	0.586 93	0.688 85	0.482 101	0.739 101	0.733 99	0.537 92

SQN_0.1%	0.569 96	0.676 89	0.696 86	0.657 88	0.497 94	0.779 86	0.424 79	0.548 101	0.515 81	0.376 102	0.902 109	0.422 84	0.357 9	0.379 103	0.456 98	0.596 89	0.659 94	0.544 84	0.685 106	0.665 110	0.556 88

TextureNet	0.566 97	0.672 91	0.664 97	0.671 84	0.494 95	0.719 99	0.445 70	0.678 83	0.411 106	0.396 100	0.935 88	0.356 98	0.225 72	0.412 100	0.535 90	0.565 96	0.636 101	0.464 103	0.794 95	0.680 107	0.568 82
Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkerhouser, Matthias Niessner, Leonidas Guibas: TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes. CVPR
DVVNet	0.562 98	0.648 93	0.700 83	0.770 57	0.586 76	0.687 103	0.333 102	0.650 87	0.514 82	0.475 86	0.906 106	0.359 97	0.223 74	0.340 105	0.442 100	0.422 109	0.668 92	0.501 96	0.708 104	0.779 84	0.534 93

Pointnet++ & Feature	0.557 99	0.735 70	0.661 98	0.686 78	0.491 96	0.744 97	0.392 90	0.539 102	0.451 99	0.375 103	0.946 65	0.376 95	0.205 81	0.403 101	0.356 105	0.553 97	0.643 98	0.497 97	0.824 91	0.756 93	0.515 97

GMLPs	0.538 100	0.495 110	0.693 88	0.647 92	0.471 99	0.793 78	0.300 105	0.477 106	0.505 84	0.358 104	0.903 108	0.327 102	0.081 111	0.472 93	0.529 92	0.448 107	0.710 74	0.509 93	0.746 99	0.737 98	0.554 89

PanopticFusion-label	0.529 101	0.491 111	0.688 92	0.604 100	0.386 106	0.632 110	0.225 116	0.705 78	0.434 103	0.293 110	0.815 114	0.348 100	0.241 68	0.499 88	0.669 76	0.507 100	0.649 95	0.442 109	0.796 94	0.602 114	0.561 85
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
subcloud_weak	0.516 102	0.676 89	0.591 111	0.609 98	0.442 102	0.774 87	0.335 101	0.597 94	0.422 105	0.357 105	0.932 94	0.341 101	0.094 110	0.298 107	0.528 93	0.473 105	0.676 89	0.495 98	0.602 112	0.721 102	0.349 114

Online SegFusion	0.515 103	0.607 101	0.644 102	0.579 103	0.434 103	0.630 111	0.353 99	0.628 92	0.440 101	0.410 98	0.762 117	0.307 104	0.167 98	0.520 81	0.403 103	0.516 99	0.565 105	0.447 107	0.678 107	0.701 104	0.514 98
Davide Menini, Suryansh Kumar, Martin R. Oswald, Erik Sandstroem, Cristian Sminchisescu, Luc van Gool: A Real-Time Learning Framework for Joint 3D Reconstruction and Semantic Segmentation. Robotics and Automation Letters Submission
3DMV, FTSDF	0.501 104	0.558 106	0.608 109	0.424 116	0.478 98	0.690 102	0.246 112	0.586 96	0.468 94	0.450 91	0.911 104	0.394 91	0.160 101	0.438 96	0.212 112	0.432 108	0.541 110	0.475 102	0.742 100	0.727 100	0.477 104

PCNN	0.498 105	0.559 105	0.644 102	0.560 105	0.420 105	0.711 101	0.229 114	0.414 107	0.436 102	0.352 106	0.941 80	0.324 103	0.155 102	0.238 112	0.387 104	0.493 101	0.529 111	0.509 93	0.813 93	0.751 95	0.504 99

3DMV	0.484 106	0.484 112	0.538 114	0.643 94	0.424 104	0.606 114	0.310 103	0.574 98	0.433 104	0.378 101	0.796 115	0.301 105	0.214 78	0.537 79	0.208 113	0.472 106	0.507 114	0.413 112	0.693 105	0.602 114	0.539 91
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGB	0.458 107	0.577 104	0.611 107	0.356 118	0.321 114	0.715 100	0.299 107	0.376 111	0.328 114	0.319 108	0.944 74	0.285 107	0.164 99	0.216 115	0.229 110	0.484 103	0.545 109	0.456 105	0.755 98	0.709 103	0.475 105
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPN	0.447 108	0.679 88	0.604 110	0.578 104	0.380 107	0.682 104	0.291 108	0.106 118	0.483 91	0.258 116	0.920 101	0.258 111	0.025 115	0.231 114	0.325 106	0.480 104	0.560 107	0.463 104	0.725 102	0.666 109	0.231 118
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproduce	0.446 109	0.474 113	0.623 105	0.463 112	0.366 109	0.651 107	0.310 103	0.389 110	0.349 112	0.330 107	0.937 85	0.271 109	0.126 107	0.285 108	0.224 111	0.350 114	0.577 104	0.445 108	0.625 110	0.723 101	0.394 110
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
SurfaceConvPF	0.442 110	0.505 109	0.622 106	0.380 117	0.342 112	0.654 106	0.227 115	0.397 109	0.367 109	0.276 112	0.924 98	0.240 112	0.198 86	0.359 104	0.262 108	0.366 111	0.581 103	0.435 110	0.640 109	0.668 108	0.398 109
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
PNET2	0.442 110	0.548 107	0.548 113	0.597 102	0.363 110	0.628 112	0.300 105	0.292 113	0.374 108	0.307 109	0.881 110	0.268 110	0.186 91	0.238 112	0.204 114	0.407 110	0.506 115	0.449 106	0.667 108	0.620 113	0.462 108

Tangent Convolutions	0.438 112	0.437 115	0.646 101	0.474 111	0.369 108	0.645 108	0.353 99	0.258 115	0.282 117	0.279 111	0.918 103	0.298 106	0.147 106	0.283 109	0.294 107	0.487 102	0.562 106	0.427 111	0.619 111	0.633 112	0.352 113
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS	0.425 113	0.525 108	0.647 100	0.522 106	0.324 113	0.488 118	0.077 119	0.712 76	0.353 111	0.401 99	0.636 119	0.281 108	0.176 94	0.340 105	0.565 88	0.175 118	0.551 108	0.398 113	0.370 119	0.602 114	0.361 112

SPLAT Net	0.393 114	0.472 114	0.511 115	0.606 99	0.311 115	0.656 105	0.245 113	0.405 108	0.328 114	0.197 117	0.927 97	0.227 114	0.000 119	0.001 120	0.249 109	0.271 117	0.510 112	0.383 115	0.593 113	0.699 105	0.267 116
Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz: SPLATNet: Sparse Lattice Networks for Point Cloud Processing. CVPR 2018
ScanNet+FTSDF	0.383 115	0.297 117	0.491 116	0.432 115	0.358 111	0.612 113	0.274 110	0.116 117	0.411 106	0.265 113	0.904 107	0.229 113	0.079 112	0.250 110	0.185 115	0.320 115	0.510 112	0.385 114	0.548 114	0.597 117	0.394 110

PointNet++	0.339 116	0.584 103	0.478 117	0.458 113	0.256 117	0.360 119	0.250 111	0.247 116	0.278 118	0.261 115	0.677 118	0.183 116	0.117 108	0.212 116	0.145 117	0.364 112	0.346 119	0.232 119	0.548 114	0.523 118	0.252 117
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
GrowSP++	0.323 117	0.114 119	0.589 112	0.499 108	0.147 119	0.555 115	0.290 109	0.336 112	0.290 116	0.262 114	0.865 113	0.102 119	0.000 119	0.037 118	0.000 120	0.000 120	0.462 116	0.381 116	0.389 118	0.664 111	0.473 106

SSC-UNet	0.308 118	0.353 116	0.290 119	0.278 119	0.166 118	0.553 116	0.169 118	0.286 114	0.147 119	0.148 119	0.908 105	0.182 117	0.064 113	0.023 119	0.018 119	0.354 113	0.363 117	0.345 117	0.546 116	0.685 106	0.278 115

ScanNet	0.306 119	0.203 118	0.366 118	0.501 107	0.311 115	0.524 117	0.211 117	0.002 120	0.342 113	0.189 118	0.786 116	0.145 118	0.102 109	0.245 111	0.152 116	0.318 116	0.348 118	0.300 118	0.460 117	0.437 119	0.182 119
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR	0.054 120	0.000 120	0.041 120	0.172 120	0.030 120	0.062 121	0.001 120	0.035 119	0.004 120	0.051 120	0.143 120	0.019 120	0.003 118	0.041 117	0.050 118	0.003 119	0.054 120	0.018 120	0.005 121	0.264 120	0.082 120

MVF-GNN	0.014 121	0.000 120	0.000 121	0.000 121	0.007 121	0.086 120	0.000 121	0.000 121	0.001 121	0.000 121	0.029 121	0.001 121	0.000 119	0.000 121	0.000 120	0.000 120	0.000 121	0.018 120	0.015 120	0.115 121	0.000 121

3D Semantic Label Benchmark